An Efficient Boosting Algorithm for Combining Preferences

Abstract

The problem of combining preferences arises in several applications, such as combining the results of di_x000B_erent search engines. This work describes an effcient algorithm for combining multiple preferences. We _x000C_rst give a formal framework for the problem. We then describe and analyze a new boosting algorithm for combining preferences called RankBoost. We also describe an effcient implementation of the algorithm for certain natural cases. We discuss two experiments we carried out to assess the performance of RankBoost. In the _x000C_rst experiment, we used the algorithm to combine di_x000B_erent WWW search strategies, each of which is a queryexpansion for a given domain. For this task, we compare the performance of RankBoost to the individual search strategies. The second experiment is a collaborative-filtering task for making movie recommendations. Here, we present results comparing RankBoost to nearest-neighbor and regression algorithms.